Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SeeUPO: Sequence-Level Agentic-RL with Convergence GuaranteesAlibaba · arXiv (Cornell University)Feb 6When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMsMicrosoft · arXiv (Cornell University)Feb 6Bridging the Indoor-Outdoor Gap: Vision-Centric Instruction-Guided Embodied Navigation for the Last MetersAlibaba · arXiv (Cornell University)Feb 6Statistical Learning from Attribution SetsAlphabet · arXiv (Cornell University)Feb 6Practical Machine Learning Autotuning for Large-Scale Collective CommunicationNVIDIA · IEEE Transactions on Parallel and Distributed SystemsFeb 6Benchmark of plankton images classification: emphasizing features extraction over classifier complexityAlphabet · Earth system science data3 citationsFeb 5Reinforcement World Model Learning for LLM-based AgentsMicrosoft · arXiv (Cornell University)3 citationsFeb 5Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-ResolutioniFlytek · arXiv (Cornell University)1 citationFeb 5Self-Improving World Modelling with Latent ActionsNVIDIA · arXiv (Cornell University)1 citationFeb 5Hyperscale FPGA Engineering Systems at MicrosoftMicrosoft · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)1 citationFeb 5Bridging the Gap: A Module-Context Modeling Methodology for Hyperscale FPGA ApplicationsMicrosoft · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)1 citationFeb 5MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language ModelsAllen Institute for AI · arXiv (Cornell University)1 citationFeb 5SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMsAlibaba · arXiv (Cornell University)1 citationFeb 5The Effects of Audio Sample Rate on Training in Large Scale Foundation Models for Time Series ForecastingNVIDIA · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)Feb 5Retrieval-Augmented Generative AI for Adaptive Data Engineering in Healthcare SystemsMeta · International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)Feb 5interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time VerificationMicrosoft · arXiv (Cornell University)Feb 5Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMsNVIDIA · arXiv (Cornell University)Feb 5OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every IterationAlibaba · arXiv (Cornell University)Feb 5Building Trustworthy AI for Enterprise Support: An Empirical Study of a RAG-Based Architectural FrameworkAlphabet · Universal Library of Innovative Research and StudiesFeb 5AI-Assisted Copilot Automation for Reliable FPGA Verification at HyperscaleMicrosoft · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA)Feb 5MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal NavigationAlibaba · arXiv (Cornell University)Feb 5NeuCLIRTech: Chinese Monolingual and Cross-Language Information Retrieval Evaluation in a Challenging DomainAllen Institute for AI · arXiv (Cornell University)Feb 5A Unified Framework for Rethinking Policy Divergence Measures in GRPOCohere · arXiv (Cornell University)Feb 5Bagpiper: Solving Open-Ended Audio Tasks via Rich CaptionsNVIDIA · arXiv (Cornell University)Feb 5DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse AutoencodersAlibaba · arXiv (Cornell University)Feb 5